Object Detection on Cityscapes to Foggy Cityscapes (val)
49.2mAPTDD
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| TDDBackbone=ResNet-502022.05 | 49.2 | 50.7 | 53.7 | 68.2 | 35.1 | 53 | 45.1 | 38.9 | 49.1 | |
| Oracle (source+target)Backbone=ResNet-502022.05 | 49.2 | 50 | 50.2 | 69.9 | 35.6 | 56.3 | 47.4 | 41 | 43.4 | |
| DSSBackbone=ResNet-502022.05 | 47.8 | 50.9 | 57.6 | 61.1 | 35.4 | 50.9 | 36.6 | 38.4 | 51.1 | |
| Oracle (target)Backbone=ResNet-502022.05 | 47.4 | 50.1 | 51.7 | 70.1 | 33.4 | 49.5 | 42.8 | 37.6 | 44.3 | |
| MKTBackbone=ResNet-502022.05 | 47.3 | 43.5 | 52 | 63.2 | 34.7 | 52.7 | 45.8 | 37.1 | 49.4 | |
| Oracle (source+target)Backbone=VGG162022.05 | 43.5 | 39.5 | 47.5 | 58.1 | 34.2 | 49.3 | 41.9 | 36.4 | 41 | |
| VISGABackbone=ResNet-502022.05 | 43.3 | 38.8 | 45.9 | 57.2 | 29.9 | 50.2 | 51.9 | 31.9 | 40.9 | |
| TDDBackbone=VGG162022.05 | 43.1 | 39.6 | 47.5 | 55.7 | 33.8 | 47.6 | 42.1 | 37 | 41.4 | |
| MeGABackbone=VGG162022.05 | 41.8 | 37.7 | 49 | 52.4 | 25.4 | 49.2 | 46.9 | 34.5 | 39 | |
| UMTBackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 41.7 | 33 | 46.7 | 48.6 | 34.1 | 56.5 | 46.8 | 30.4 | 37.3 | |
| UMTBackbone=VGG162022.05 | 41.7 | 33 | 46.7 | 48.6 | 34.1 | 56.5 | 46.8 | 30.4 | 37.3 | |
| Oracle (target)Backbone=VGG162022.05 | 41.3 | 39.1 | 44.9 | 56.7 | 33.3 | 50.4 | 34.8 | 32.3 | 39 | |
| SFABackbone=ResNet-502022.05 | 41.3 | 46.5 | 48.6 | 62.6 | 25.1 | 46.2 | 29.4 | 28.3 | 44 | |
| SAPNetBackbone=VGG162022.05 | 40.9 | 40.8 | 46.7 | 59.8 | 24.3 | 46.8 | 37.5 | 30.4 | 40.7 | |
| UMTSCABackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 40.4 | 33.8 | 47.3 | 49.8 | 30 | 48.2 | 42.1 | 33 | 38.9 | |
| OracleBackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 40.3 | 33.2 | 45.9 | 49.7 | 35.6 | 50 | 37.4 | 34.7 | 36.2 | |
| HTCNBackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 39.8 | 33.2 | 47.5 | 47.9 | 31.6 | 47.4 | 40.9 | 32.3 | 37.1 | |
| HTCNBackbone=VGG162022.05 | 39.8 | 33.2 | 47.5 | 47.9 | 31.6 | 47.4 | 40.9 | 32.3 | 37.1 | |
| AFANBackbone=ResNet-502022.05 | 39.6 | 42.5 | 44.6 | 57 | 26.4 | 48 | 28.3 | 33.2 | 37.1 | |
| GPABackbone=ResNet-502022.05 | 39.5 | 32.9 | 46.7 | 54.1 | 24.7 | 45.7 | 41.1 | 32.4 | 38.7 | |
| UMTSCBackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 39.2 | 33.4 | 45.9 | 50.6 | 31.9 | 43.4 | 36.4 | 33.7 | 38 | |
| ATFBackbone=VGG162022.05 | 38.7 | 34.6 | 47 | 50 | 23.7 | 43.3 | 38.7 | 33.4 | 38.8 | |
| RPABackbone=VGG162022.05 | 38.5 | 33.4 | 44.3 | 50.1 | 29.9 | 44.8 | 39.1 | 29.9 | 36.3 | |
| SCLBackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 37.9 | 31.6 | 44 | 44.8 | 30.4 | 41.8 | 40.7 | 33.6 | 36.2 | |
| CRDABackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 37.4 | 32.9 | 43.8 | 49.2 | 27.2 | 45.1 | 36.4 | 30.3 | 34.6 | |
| ICR-CCRBackbone=VGG162022.05 | 37.4 | 32.9 | 43.8 | 49.2 | 27.2 | 45.1 | 36.4 | 30.3 | 34.6 | |
| CDN2020.03 | 36.6 | 35.8 | 45.7 | 50.9 | 30.1 | 42.5 | 29.8 | 30.8 | 36.5 | |
| CDNBackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 36.6 | 35.8 | 45.7 | 50.9 | 30.1 | 42.5 | 29.8 | 30.8 | 36.5 | |
| CDNBackbone=VGG162022.05 | 36.6 | 35.8 | 45.7 | 50.9 | 30.1 | 42.5 | 29.8 | 30.8 | 36.5 | |
| SC-DABackbone=ResNet-502022.05 | 35.9 | 33.8 | 42.1 | 52.1 | 26.8 | 42.5 | 26.5 | 29.2 | 34.5 | |
| iFANBackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 35.3 | 32.6 | 40 | 48.5 | 27.9 | 45.5 | 31.7 | 22.8 | 33 | |
| SW-DABackbone=ResNet-502022.05 | 35.3 | 31.8 | 44.3 | 48.9 | 21 | 43.8 | 28 | 28.9 | 35.8 | |
| MTORBackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 35.1 | 30.6 | 41.4 | 44 | 21.9 | 38.6 | 40.6 | 28.3 | 35.6 | |
| MTORBackbone=ResNet-502022.05 | 35.1 | 30.6 | 41.4 | 44 | 21.9 | 38.6 | 40.6 | 28.3 | 35.6 | |
| D&MatchBackbone=ResNet-502022.05 | 34.9 | 31.8 | 40.5 | 51 | 20.9 | 41.8 | 34.3 | 26.6 | 32.4 | |
| SWDA2020.03 | 34.8 | 30.3 | 42.5 | 44.6 | 24.5 | 36.7 | 31.6 | 30.2 | 35.8 | |
| DDMRL2020.03 | 34.6 | 30.8 | 40.5 | 44.3 | 27.2 | 38.4 | 34.5 | 28.4 | 32.2 | |
| DMBackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 34.6 | 30.8 | 40.5 | 44.3 | 27.2 | 38.4 | 34.5 | 28.4 | 32.2 | |
| D&MatchBackbone=VGG162022.05 | 34.6 | 30.8 | 40.5 | 44.3 | 27.2 | 38.4 | 34.5 | 28.4 | 32.2 | |
| SWDABackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 34.3 | 29.9 | 42.3 | 43.5 | 24.5 | 36.2 | 32.6 | 30 | 35.3 | |
| SWDABackbone=VGG162022.05 | 34.3 | 29.9 | 42.3 | 43.5 | 24.5 | 36.2 | 32.6 | 30 | 35.3 | |
| MAFBackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 34 | 28.2 | 39.5 | 43.9 | 23.8 | 39.9 | 33.3 | 29.2 | 33.9 | |
| SCDA2020.03 | 33.8 | 33.5 | 38 | 48.5 | 26.5 | 39 | 23.3 | 28 | 33.6 | |
| SCDABackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 33.8 | 33.5 | 38 | 48.5 | 26.5 | 39 | 23.3 | 28 | 33.6 | |
| SCDABackbone=VGG162022.05 | 33.8 | 33.5 | 38 | 48.5 | 26.5 | 39 | 23.3 | 28 | 33.6 | |
| WDBackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 33.1 | 30.2 | 42 | 44.2 | 22.2 | 39.9 | 26.5 | 25.4 | 34.4 | |
| DA-FasterBackbone=ResNet-502022.05 | 32 | 29.2 | 40.4 | 43.4 | 19.7 | 38.3 | 28.5 | 23.7 | 32.7 | |
| DT2020.03 | 31.5 | 25.4 | 39.3 | 42.4 | 24.9 | 40.4 | 23.1 | 25.9 | 30.4 | |
| PFBackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 28.9 | — | — | — | — | — | — | — | — | |
| UMTSBackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 28.5 | 27.9 | 38.2 | 36.1 | 21.5 | 30.1 | 20.2 | 22.4 | 31.3 | |
| source onlyBackbone=ResNet-502022.05 | 28.3 | 36.9 | 36.1 | 44.5 | 21.7 | 32.3 | 9.2 | 21.5 | 32.4 | |
| DA-Faster2020.03 | 27.9 | 25 | 31 | 40.5 | 22.1 | 35.3 | 20.2 | 20 | 27.1 | |
| DA-FasterBackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 27.6 | 25 | 31 | 40.5 | 22.1 | 35.3 | 20.2 | 20 | 27.1 | |
| DA-FasterBackbone=VGG162022.05 | 27.6 | 25 | 31 | 40.5 | 22.1 | 35.3 | 20.2 | 20 | 27.1 | |
| Source2020.03 | 26.1 | 29.3 | 31.9 | 43.5 | 15.8 | 27.4 | 9 | 20.3 | 29.9 | |
| source onlyBackbone=VGG162022.05 | 25.8 | 28.5 | 34.2 | 39.9 | 14.7 | 26.3 | 11.4 | 23.4 | 28.3 | |
| Source OnlyBackbone=VGG16, Architecture=Faster R-CNN, Pre-trained=ImageNet2020.03 | 21.8 | 24.3 | 31.5 | 27.2 | 12.1 | 24.7 | 9.1 | 16.4 | 29 |